Statistical Modeling of Vehicles Collision When Using a DVR with the Function of Signaling about Dangerous Motion of the Vehicle to the Oncoming Lane

International science and technology conference "Earth science"

Varnavsky, A.N.^1

National Research University Higher, School of Economics, Moscow

101000, Russia^1

关键词: Alarm parameters;    Algorithm parameters;    Collision probability;    Collision warning;    Parameters dynamics;    Statistical modeling;    Threshold levels;    Vehicles collision;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/272/3/032052/pdf
DOI  :  10.1088/1755-1315/272/3/032052

来源: IOP

【 摘 要 】

There is a way of using a DVR for automatic collision warning of vehicles moving on the oncoming lane. This way is based on the analysis of the images parameters dynamics of vehicles on the road obtained with the help of a video recorder. The analysis determined the value that is compared with a threshold level. Its excess indicates an increased risk of collision of vehicles. At this time, the driver is notified of the need to change the parameters of the vehicle and the restructuring. When using this method, the question remains concerning the adjustment of the algorithm parameters. The aim of the work is to simulate statistically the probability of an accident with timely alarm to the driver about the risk of collision, as well as to study the effect of the alarm parameters on the probability of collision of vehicles moving on the oncoming lane. As a result of modeling, a series of dependencies on the collision probability of different parameters of the alarm algorithm, the car, the driver and the car movement is received. Based on the obtained dependences, it will be possible to conclude about the optimal setting of the parameters of the driver's alarm about the possibility of a collision, taking into account the status and performance of the road system, the car and the driver.